Document Type

Article

Publication Date

8-1997

Abstract

This article investigates algorithmic learning, in the limit, of correct programs for recursive functionsffrom both input/output examples offand several interesting varieties ofapproximateadditional (algorithmic) information aboutf. Specifically considered, as such approximate additional information aboutf, are Rose's frequency computations forfand several natural generalizations from the literature, each generalization involving programs for restricted trees of recursive functions which havefas a branch. Considered as the types of trees are those with bounded variation, bounded width, and bounded rank. For the case of learning final correct programs for recursive functions, EX-learning, where the additional information involves frequency computations, an insightful and interestingly complex combinatorial characterization of learning power is presented as a function of the frequency parameters. For EX-learning (as well as for BC-learning, where a finalsequenceof correct programs is learned), for the cases of providing the types of additional information considered in this paper, the maximal probability is determined such that the entire class of recursive functions is learnable with that probability.

Comments

An extended abstract of this publication appeared in:Computational Learning Theory-Second European Conference, EuroCOLT'95. Editor: Paul Vitányi. Lecture Notes in Artificial Intelligence 904, pp. 140–153, Springer-Verlag, Berlin, 1995.

DOI

10.1006/jcss.1997.1508

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.